Speed control of BL DC Motor using Neural Network in MATLAB

Speed control of BL DC Motor using Neural Network in MATLAB

MATLABSolutions demonstrate how to Implementation of BLDC motor has surpassed other motors as the demand for high efficiency, high power factor, precise speed and torque control and low maintenance increases. BLDC motor has become predominantly significant in applications such as electric trains, electric automotive, aviation and robotics Since the BLDC motors does not require Commutator and due to its transcendent electrical and mechanical ascribes and its ability to work in risky conditions it is more reliable than the DC engine.

Abstract

BLDC motor has surpassed other motors as the demand for high efficiency, high power factor, precise speed and torque control and low maintenance increases. BLDC motor has become predominantly significant in applications such as electric trains, electric automotive, aviation and robotics Since the BLDC motors does not require Commutator and due to its transcendent electrical and mechanical ascribes and its ability to work in risky conditions it is more reliable than the DC engine. There are a lot of parameters which need to be in focus while talking about a speed controller performance like starting current, starting torque, rise time, etc., This paper presents the design and performance and the comparative analysis between the speed control of electronically commuted Brushless DC motor (BLDC) using conventional controllers like Proportional Integrative (PI) controller, Fuzzy PI controller, Artificial Neural Network speed controllers for the BLDC motors will be proposed. A simulation study is conducted to evaluate the efficiency of the proposed speed controllers. Further, a comparative study is performed to validate the system effectiveness. The response of the system can be observed from the above controllers with the help of MATLAB / SIMULINK.

Introduction

The rapid requirement of motor drives with the new technology in the various industries isincreases day by day. There is great demand for efficient variable speed, long term stability and good transient performance of motor drives. The dc motor may be categorized according to the commutation circuit. One is traditionally DC motor which is mechanically commutated and other is Brushless DC motor (BLDC) having an electronically commutated with sensor or sensor-less system.

The BLDC motor has a rotating permanent magnet and stationary armature1. Brushless DC Motors (BLDC) are widely used in many applications such as automotive, computer, industrial, aerospace etc. BLDC Motors have several advantages over brushed DC Motor. They have lower maintenance due to the elimination of the mechanical commutator and they have a high power density which makes them ideal for high torque to weight ratio applications. Compared to induction machines, they have lower inertia allowing for faster dynamic response to reference commands. Also, they are more efficient due to the permanent magnets which results in virtually zero rotor losses It has many advantages such as simple structure, high reliability, small size, high torque and simple structure. It is mainly applicable for high performance drives.

Generally the performance of motor is affected by sudden change in unknown load or speed. But as the BLDC motor drives are nonlinear in nature, they require an improved or modified controller that can adapt a nonlinear condition and achieve the desired performance. So to encounter this problem controller is required. Because of the simplicity in tuning, the PI controller are until now are mostly useful controller in industries.
The PI controller is carried out from the input and feedback signal. And then this error passes through the proportional integrative function one by one, so that the speed error can be reduced and get the desired performance. But this controller is fails to operate in dynamic conditions. Also it has some operating condition issue. While comparing with the Fuzzy logic controller, PI controller takes large number of peak overshoot that affects the system performance. The Fuzzy tunned with conventional PI controller improves the dynamic as well as steady state behavior and also it improves the system performance.